© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3.5-9B Base
    5. 15-QWENSCOPE-RES-64K
    7. 25868
    Prev
    Next
    INDEX
    Explanations

    organizations and institutions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    lend
    -0.08
    нÑijм
    -0.07
    èį¡
    -0.07
    toor
    -0.07
    æŃ¤äºº
    -0.07
    åī¯éĥ¨éķ¿
    -0.07
    æīij
    -0.07
    æľīç½ijåıĭ
    -0.07
    lai
    -0.07
    aime
    -0.07
    POSITIVE LOGITS
    纷纷
    0.10
    åĨħéĥ¨çļĦ
    0.10
    åĢĴéĹŃ
    0.09
    åĨħéĥ¨
    0.09
     interiors
    0.09
     themselves
    0.09
    ç«ŀ缸
    0.08
     hiring
    0.08
    主ä½ĵ责任
    0.08
    èģĺ
    0.08
    Activations Density 0.413%

    No Known Activations